Share Email Print

Proceedings Paper

Research on optimization method of deep neural network
Author(s): Pengfei Liu; Huaici Zhao; Feidao Cao
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Image recognition technology has been widely applied and played an important role in various fields nowadays. Because of multi-layer structure of deep network can use a more concise way to express complex functions, deep neural network (DNN) will be applied to the image recognition to improve the accuracy of image classification. Analysis the existing problems of deep neural network. Then put forward new approaches to solve the gradient vanishing and over-fitting problems. The experimental results which verified on the MNIST, show that our proposed approaches can improve the classification accuracy greatly and accelerate the convergence speed. Compared to support vector machine (SVM), the optimized model of the neural network is not only effective, but also converged quickly.

Paper Details

Date Published: 15 November 2017
PDF: 6 pages
Proc. SPIE 10605, LIDAR Imaging Detection and Target Recognition 2017, 106052T (15 November 2017); doi: 10.1117/12.2294481
Show Author Affiliations
Pengfei Liu, Shenyang Institute of Automation (China)
Univ. of Chinese Academy of Sciences (China)
Huaici Zhao, Shenyang Institute of Automation (China)
Feidao Cao, Shenyang Institute of Automation (China)
Univ. of Chinese Academy of Sciences (China)

Published in SPIE Proceedings Vol. 10605:
LIDAR Imaging Detection and Target Recognition 2017
Yueguang Lv; Weimin Bao; Weibiao Chen; Zelin Shi; Jianzhong Su; Jindong Fei; Wei Gong; Shensheng Han; Weiqi Jin; Jian Yang, Editor(s)

© SPIE. Terms of Use
Back to Top